MetaFruit Meets Foundation Models: Leveraging a Comprehensive Multi-Fruit Dataset for Advancing Agricultural Foundation Models

More code instruction still in progress 🚀, we appreciate any suggestions ❤️.

Training command example:

./tools/dist_train.sh configs/grounding_dino/grounding_dino_swin-t_finetune_8xb2_20e_fruit.py 3 --work-dir ./work_dirs/

Reference

mmdetection.

Liu, Shilong, et al. "Grounding dino: Marrying dino with grounded pre-training for open-set object detection." arXiv preprint arXiv:2303.05499 (2023).

Citation

@article{li2024metafruit,
  title={MetaFruit Meets Foundation Models: Leveraging a Comprehensive Multi-Fruit Dataset for Advancing Agricultural Foundation Models},
  author={Li, Jiajia and Lammers, Kyle and Yin, Xunyuan and Yin, Xiang and He, Long and Lu, Renfu and Li, Zhaojian},
  journal={arXiv preprint arXiv:2407.04711},
  year={2024}
}

@inproceedings{li2024advancing,
  title={Advancing Orchard Fruit Detection: An Innovative Agricultural Foundation Model Approach},
  author={Li, Jiajia and Lammers, Kyle and Yin, Xunyuan and Yin, Xiang and He, Long and Lu, Renfu and Li, Zhaojian},
  booktitle={2024 ASABE Annual International Meeting},
  pages={1},
  year={2024},
  organization={American Society of Agricultural and Biological Engineers}
}